claude-memory-mcp
Provides persistent local memory for AI assistants using SQLite and semantic search, enabling context-aware conversations.
README
🧠 claude-memory-mcp - Give your AI persistent local memory
claude-memory-mcp acts as a bridge between your AI assistant and your computer. It creates a private storage space for your conversations and data. You keep full control over your information because everything stays on your machine. This tool uses a database to remember past details so your AI works better over time.
💾 Why use local memory?
Standard AI assistants often forget previous tasks once you close a chat. This tool solves that problem. It records key facts from your interactions into a local file. When you ask a question later, the AI checks this file to find relevant context. You gain a smarter assistant that recalls your preferences and project details.
- Private: Your data never leaves your computer.
- Efficient: It uses semantic search to find information fast.
- Persistent: Your notes stay on your hard drive forever.
- Simple: No complex setup or cloud accounts are needed.
🛠 Prerequisites
You need a few basic things to run this software on your Windows computer:
- Windows 10 or Windows 11.
- At least 100MB of free disk space.
- A basic understanding of how to open a folder and run a file.
- Your preferred AI application that supports the Model Context Protocol.
📥 Downloading the software
You need to download the installer from our release page. Visit the link below to find the most recent version of the software.
Download the latest installer here
- Open the link above in your web browser.
- Look for the section labeled "Assets".
- Find the file that ends with
.exefor Windows. - Click the file name to start the download.
- Save the file to your "Downloads" folder.
⚙️ Installation steps
Follow these steps to set up the tool on your system:
- Locate the downloaded file in your "Downloads" folder.
- Double-click the file to start the installation.
- Follow the instructions on the screen.
- Select "Yes" if Windows asks for permission to run the software.
- The installer completes the setup process automatically.
- You will see a small icon in your taskbar once the program runs successfully.
🔗 Connecting to your AI
The software requires a connection to your AI program. Most modern AI tools feature a "Settings" or "Configuration" section.
- Open your AI program.
- Look for "Model Context Protocol" or "MCP" settings.
- Click "Add New Server".
- Enter a name for the connection, such as "My Local Memory".
- Point the setting to the file path where you installed the claude-memory-mcp software.
- Save the settings and restart your AI program.
The AI will now show a notification that it connected to your new memory server. It builds an initial index of your data in the background.
📁 How the data works
The application creates a small file called memory.db in your documents folder. This file uses SQLite technology. SQLite is a industry standard that handles data reliably on local computers. You do not need to open or edit this file directly. The AI manages all read and write operations. Because the file lives on your own hard drive, you can move it, back it up, or delete it whenever you choose.
🔍 Understanding semantic search
Semantic search allows the AI to understand the meaning of your words rather than just matching exact phrases. For example, if you mentioned "project planning" in a meeting three weeks ago, you only need to ask the AI about "our project goals." The tool understands the relationship between these terms and retrieves the correct information from your past conversations. This works even if you used different words to describe the same idea.
🛡 Privacy and security
We built this tool with the principle of local-first computing. You do not need an account or an API key for any third-party service. The software collects no information. It sends no data to our servers. Every byte of memory stays on your device. This keeps your personal notes and work files safe from external access.
🔧 Troubleshooting
If the AI fails to connect, verify the following items:
- Check that the installer finished correctly.
- Ensure your AI program is up to date.
- Restart your computer to clear any file locks.
- Verify that your firewall is not blocking the application.
If you encounter persistent issues, check the "Issues" tab on our main repository page to see if others have faced the same situation.
Keywords: claude, collaborate, local-first, mcp, mcp-server, memory, semantic-search, sqlite, student-vscode, typescript
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.